Christian Sallaberry

Maxime Masson, Rodrigo Agerri, Christian Sallaberry et al.

The rising influence of social media platforms in various domains, including tourism, has highlighted the growing need for efficient and automated Natural Language Processing (NLP) strategies to take advantage of this valuable resource. However, the transformation of multilingual, unstructured, and informal texts into structured knowledge still poses significant challenges, most notably the never-ending requirement for manually annotated data to train deep learning classifiers. In this work, we study different NLP techniques to establish the best ones to obtain competitive performances while keeping the need for training annotated data to a minimum. To do so, we built the first publicly available multilingual dataset (French, English, and Spanish) for the tourism domain, composed of tourism-related tweets. The dataset includes multilayered, manually revised annotations for Named Entity Recognition (NER) for Locations and Fine-grained Thematic Concepts Extraction mapped to the Thesaurus of Tourism and Leisure Activities of the World Tourism Organization, as well as for Sentiment Analysis at the tweet level. Extensive experimentation comparing various few-shot and fine-tuning techniques with modern language models demonstrate that modern few-shot techniques allow us to obtain competitive results for all three tasks with very little annotation data: 5 tweets per label (15 in total) for Sentiment Analysis, 30 tweets for Named Entity Recognition of Locations and 1K tweets annotated with fine-grained thematic concepts, a highly fine-grained sequence labeling task based on an inventory of 315 classes. We believe that our results, grounded in a novel dataset, pave the way for applying NLP to new domain-specific applications, reducing the need for manual annotations and circumventing the complexities of rule-based, ad-hoc solutions.

Eric Kergosien, Marie-Noëlle Bessagnet, Maguelonne Teisseire et al.

The TERRE-ISTEX project aims at identifying the evolution of research working relation to study areas, disciplinary crossings and concrete research methods based on the heterogeneous digital content available in scientific corpora. The project is divided into three main actions: (1) to identify the periods and places which have been the subject of empirical studies, and which reflect the publications resulting from the corpus analyzed, (2) to identify the thematics addressed in these works and (3) to develop a web-based geographical information retrieval tool (GIR). The first two actions involve approaches combining Natural languages processing patterns with text mining methods. By crossing the three dimensions (spatial, thematic and temporal) in a GIR engine, it will be possible to understand what research has been carried out on which territories and at what time. In the project, the experiments are carried out on a heterogeneous corpus including electronic thesis and scientific articles from the ISTEX digital libraries and the CIRAD research center.

Eric Kergosien, Amin Farvardin, Maguelonne Teisseire et al.

The TERRE-ISTEX project aims to identify scientific research dealing with specific geographical territories areas based on heterogeneous digital content available in scientific papers. The project is divided into three main work packages: (1) identification of the periods and places of empirical studies, and which reflect the publications resulting from the analyzed text samples, (2) identification of the themes which appear in these documents, and (3) development of a web-based geographical information retrieval tool (GIR). The first two actions combine Natural Language Processing patterns with text mining methods. The integration of the spatial, thematic and temporal dimensions in a GIR contributes to a better understanding of what kind of research has been carried out, of its topics and its geographical and historical coverage. Another originality of the TERRE-ISTEX project is the heterogeneous character of the corpus, including PhD theses and scientific articles from the ISTEX digital libraries and the CIRAD research center.

Van Tien Nguyen, Christian Sallaberry, Mauro Gaio

We propose in this paper a method for measuring the similarity between ontological concepts and terms. Our metric can take into account not only the common words of two strings to compare but also other features such as the position of the words in these strings, or the number of deletion, insertion or replacement of words required for the construction of one of the two strings from each other. The proposed method was then used to determine the ontological concepts which are equivalent to the terms that qualify toponymes. It aims to find the topographical type of the toponyme.